Multiple-choice Question Answering
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
0Δ Accuracy
6
Feb 26, 2026
58MMLU Accuracy Gain (Absolute)
6
Jun 19, 2026
58.13Accuracy
6
Feb 26, 2026
37.47Score
6
Feb 26, 2026
57.92ARC-E (Italian)
6
Feb 26, 2026
73.7Accuracy
6
Feb 26, 2026
30.7High School Microeconomics Accuracy
6
Feb 26, 2026
65.89Accuracy
6
Feb 26, 2026
73.668Mean Accuracy
5
Jul 2, 2026
91.84Accuracy
5
Jun 30, 2026
98.18Accuracy
5
Jun 30, 2026
94.83Accuracy
5
Jun 30, 2026
50.8Accuracy (MMLU T5)
5
Apr 23, 2026
52.3Accuracy
5
Apr 23, 2026
25.2Accuracy
5
Apr 23, 2026
23.5Accuracy
5
Apr 23, 2026
96.35Accuracy
5
Apr 16, 2026
86.12IoU
5
Apr 16, 2026
89.6Accuracy
5
May 19, 2026
85.09Accuracy
5
Mar 10, 2026
77.7Average Score (Non-STEM)
5
Feb 26, 2026
91.38Accuracy
5
Feb 26, 2026
81Pass@1 Acc
5
Feb 26, 2026
65Pass@1 Accuracy
5
Feb 26, 2026
81Pass@1 Accuracy
5
Feb 26, 2026